AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions

Yiting Qu, Ziqing Yang, Yihan Ma, Michael Backes, Savvas Zannettou, Yang Zhang

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Multi-subject personalization · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
apply Gaussian blur followed by histogram equalization before moderation (ablation)GPT-4o · Hateful Illusiondetection accuracy: 0.03 -> 0.70Improved
apply Gaussian blur followed by histogram equalization before moderation (ablation)Q16 · Hateful Illusiondetection accuracy: 0.21 -> 0.82Improved
use chain-of-thought prompting instead of zero-shot for VLM moderation (ablation)VLMs · Hateful Illusiondetection accuracy: best 0.034 -> 0.102 (hate speech)Mixed
full fine-tuning of CLIP backbone for prompt learning (ablation)CLIP prompt-learning classifier · Hateful Illusion test splitaccuracy: 0.637 -> 0.938Improved
full fine-tuning of CLIP backbone for linear probing (ablation)CLIP linear probe · Hateful Illusion test splitaccuracy: 0.622 -> 0.823Improved
hide hate messages inside optical illusions rather than showing them directlyQ16 classifier · Hate speechdetection accuracy: 0.696 -> 0.209Hurt
add optical-illusion cues to zero-shot VLM prompts (ablation)VLMs · Hateful Illusiondetection accuracyNo clear effect
increase ControlNet guidance scale (ablation)hateful illusion generation · Hateful illusion generationpercentage of hateful illusionsImproved
re-enable Stable Diffusion safety checker during generationStable Diffusion · generated hateful illusionsshare of images blocked: blocks 3.0%No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy